From 12f97cf0676cbbb8e8aacad576eeafc2ea06c839 Mon Sep 17 00:00:00 2001 From: John Kaiser <35939694+CoveMiner@users.noreply.github.com> Date: Tue, 5 May 2020 11:43:27 -0700 Subject: [PATCH] Update surface-book-quadro.md --- devices/surface/surface-book-quadro.md | 37 ++++++++++++-------------- 1 file changed, 17 insertions(+), 20 deletions(-) diff --git a/devices/surface/surface-book-quadro.md b/devices/surface/surface-book-quadro.md index de98c89975..f6ca19dfcb 100644 --- a/devices/surface/surface-book-quadro.md +++ b/devices/surface/surface-book-quadro.md @@ -1,6 +1,6 @@ --- title: Surface Book 3 GPU technical overview -description: This article provides a technical evaluation of GPU capabilities across Surface Book 3 13-inch and 14-inch models. +description: This article describes the advanced capabilities enabled by Nvidia Quadro RTX 3000 in select Surface Book 3 for Business 15-inch models. ms.prod: w10 ms.mktglfcycl: manage ms.localizationpriority: medium @@ -11,34 +11,33 @@ ms.topic: article ms.date: 5/06/2020 ms.reviewer: brecords manager: laurawi -ms.audience: itpro +audience: itpro --- # Surface Book 3 Quadro RTX 3000 technical overview -Surface Book 3 powered by the NVIDIA® Quadro RTX™3000 GPU is built for professionals who need real-time rendering, AI acceleration, and advanced graphics and compute performance in a portable form factor. Quadro RTX 3000 fundamentally changes what you can do with the new Surface Book 3: +Surface Book 3 for Business powered by the NVIDIA® Quadro RTX™ 3000 GPU is built for professionals who need real-time rendering, AI acceleration, and advanced graphics and compute performance in a portable form factor. Quadro RTX 3000 fundamentally changes what you can do with the new Surface Book 3: - **Ray Tracing** - Produce stunning renders, designs and animations faster than ever before with 30 RT Cores for hardware-accelerated ray tracing. -- **Artificial Intelligence** - Remove redundant, tedious tasks and compute intensive work with 240 Tensor Cores for GPU-accelerated AI. -- **Advanced Graphics and Compute Technology** - Experience remarkable speed and interactivity during your most taxing graphics and compute workloads with 1,920 CUDA Cores and 6GB of GDDR6 memory. - +- **Artificial Intelligence** - Remove redundant, tedious tasks and compute intensive work with 240 Tensor Cores for GPU-accelerated AI. +- **Advanced Graphics and Compute Technology** - Experience remarkable speed and interactivity during your most taxing graphics and compute workloads with 1,920 CUDA Cores and 6GB of GDDR6 memory. ## Enterprise grade solution Of paramount importance to commercial customers, Quadro RTX 3000 brings a fully professional grade solution that combines accelerated ray tracing and deep learning capabilities with an integrated enterprise level management and support solution. Quadro drivers are tested and certified for more than 100 professional applications by leading ISVs providing an additional layer of quality assurance to validate stability, reliability, and performance. -Quadro includes an additional layer of dedicated enterprise tools for remote management of Surface Book 3 devices with Quadro RTX 3000. IT admins can remotely configure graphics systems, save/restore configurations, continuously monitor graphics systems and perform remote troubleshooting if necessary. These capabilities along with deployment tools help maximize uptime and minimize IT support requirements. +Quadro includes dedicated enterprise tools for remote management of Surface Book 3 devices with Quadro RTX 3000. IT admins can remotely configure graphics systems, save/restore configurations, continuously monitor graphics systems and perform remote troubleshooting if necessary. These capabilities along with deployment tools help maximize uptime and minimize IT support requirements. -NVIDIA develops and maintains Quadro Optimal Drivers for Enterprise (ODE) that are tuned, tested, and validated to provide enterprise level stability, reliability, availability, and support with extended product availability. Each driver release involves more than 2000 man days of testing with professional applications test suites and test cases, as well as WHQL certification. Security threats are continually monitored, and regular security updates are released to protect against newly discovered vulnerabilities. In addition, Quadro drivers undergo an additional layer of testing by Surface engineering prior to release via Windows Update. +NVIDIA develops and maintains Quadro Optimal Drivers for Enterprise (ODE) that are tuned, tested, and validated to provide enterprise level stability, reliability, availability, and support with extended product availability. Each driver release involves more than 2,000 man days of testing with professional applications test suites and test cases, as well as WHQL certification. Security threats are continually monitored, and regular security updates are released to protect against newly discovered vulnerabilities. In addition, Quadro drivers undergo an additional layer of testing by Surface engineering prior to release via Windows Update. ## Built for compute-intensive workloads Surface Book 3 with Quadro RTX 3000 delivers the best graphics performance of any Surface laptop, enabling advanced professionals to work from anywhere. -- **Creative professionals such as designers and animators.** Quadro RTX enables real-time cinematic-quality rendering through Turing-optimized ray tracing APIs such as NVIDIA OptiX, Microsoft DXR and Vulkan. +- **Creative professionals such as designers and animators.** Quadro RTX enables real-time cinematic-quality rendering through Turing-optimized ray tracing APIs such as NVIDIA OptiX, Microsoft DXR, and Vulkan. - **Architects and engineers using large, complex computer aided design (CAD) models and assemblies.** The RTX platform features the new NGX SDK to infuse powerful AI-enhanced capabilities into visual applications. This frees up time and resources through intelligent manipulation of images, automation of repetitive tasks, and optimization of compute-intensive processes. -- **Software developers across manufacturing, media & entertainment, medical, and other industries.** Quadro RTX speeds application development with ray tracing, deep learning, and rasterization capabilities through industry-leading software SDKs and APIs. **** +- **Software developers across manufacturing, media & entertainment, medical, and other industries.** Quadro RTX speeds application development with ray tracing, deep learning, and rasterization capabilities through industry-leading software SDKs and APIs. - **Data scientists using Tensor Cores and CUDA cores to accelerate computationally intensive tasks and other deep learning operations.** By using sensors, increased connectivity, and deep learning, researchers and developers can enable AI applications for everything from autonomous vehicles to scientific research. @@ -47,17 +46,17 @@ Surface Book 3 with Quadro RTX 3000 delivers the best graphics performance of an | **Component** | **Description** | | --------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | RT cores | Dedicated hardware-based ray-tracing technology allows the GPU to render film quality, photorealistic objects and environments with physically accurate shadows, reflections, and refractions. The real-time ray-tracing engine works with NVIDIA OptiX, Microsoft DXR, and Vulkan APIs to deliver a level of realism far beyond what is possible using traditional rendering techniques. RT cores accelerate the Bounding Volume Hierarchy (BVH) traversal and ray casting functions using low number of rays casted through a pixel. | -| Enhanced tensor cores | Mixed-precision cores purpose-built for deep learning matrix arithmetic, deliver 8x TFLOPS for training, compared to previous generation. Quadro RTX 3000 utilizes 240 Tensor Cores; each Tensor Core performs 64 floating point fused multiply-add (FMA) operations per clock, and each SM performs a total of 1024 individual floating-point operations per clock. In addition to supporting FP16/FP32 matrix operations, new Tensor Cores added INT8 (2048 integer operations per clock) and experimental INT4 and INT1 (binary) precision modes for matrix operations. | -| Turing optimized software | Deep learning frameworks such as the Microsoft Cognitive Toolkit (CNTK). Caffe2, MXNet, TensorFlow, and others deliver dramatically faster training times and higher multi-node training performance. GPU accelerated libraries such as cuDNN, cuBLAS, and TensorRT deliver higher performance for both deep learning inference and High-Performance Computing (HPC) applications. | +| Enhanced tensor cores | Mixed-precision cores purpose-built for deep learning matrix arithmetic, deliver 8x TFLOPS for training compared with previous generation. Quadro RTX 3000 utilizes 240 Tensor Cores; each Tensor Core performs 64 floating point fused multiply-add (FMA) operations per clock, and each streaming multiprocessor (SM) performs a total of 1,024 individual floating-point operations per clock. In addition to supporting FP16/FP32 matrix operations, new Tensor Cores added INT8 (2,048 integer operations per clock) and experimental INT4 and INT1 (binary) precision modes for matrix operations. | +| Turing optimized software | Deep learning frameworks such as the Microsoft Cognitive Toolkit (CNTK), Caffe2, MXNet, TensorFlow, and others deliver significantly faster training times and higher multi-node training performance. GPU accelerated libraries such as cuDNN, cuBLAS, and TensorRT deliver higher performance for both deep learning inference and High-Performance Computing (HPC) applications. | | NVIDIA CUDA parallel computing platform | Natively execute standard programming languages like C/C++ and Fortran, and APIs such as OpenCL, OpenACC and Direct Compute to accelerate techniques such as ray tracing, video and image processing, and computation fluid dynamics. | | Advanced streaming multiprocessor (SM) architecture | Combined shared memory and L1 cache improve performance significantly, while simplifying programming and reducing the tuning required to attain best application performance. | -| High performance GDDR6 and GDDR5 Memory | Quadro RTX 3000 features 6GB of frame buffer making it the ideal platform for handling large datasets and latency-sensitive applications. | +| High performance GDDR6 Memory | Quadro RTX 3000 features 6GB of frame buffer making it the ideal platform for handling large datasets and latency-sensitive applications. | | Single instruction, multiple thread (SIMT) | New independent thread scheduling capability enables finer-grain synchronization and cooperation between parallel threads by sharing resources among small jobs. | | Mixed-precision computing | 16-bit floating-point precision computing enables the training and deployment of larger neural networks. With independent parallel integer and floating-point data paths, the Turing SM handles workloads more efficiently using a mix of computation and addressing calculations. | -| Dynamic load balancing | Dynamically allocate GPU resources for graphics and compute tasks as needed to maximize resource utilization. | +| Dynamic load balancing | Provides dynamic allocation capabilities of GPU resources for graphics and compute tasks as needed to maximize resource utilization. | | Compute preemption | Preemption at the instruction-level provides finer grain control over compute tasks to prevent long-running applications from either monopolizing system resources or timing out. | -| H.264, H.265 and HEVC encode/decode engines | Deliver faster than real-time performance for transcoding, video editing, and other encoding applications with two dedicated H.264 and HEVC encode engines and a dedicated decode engine that are independent of 3D/compute pipeline. | -| NVIDIA GPU boost 4.0 | Automatically maximize application performance without exceeding the power and thermal envelope of the GPU. Allows applications to stay within the boost clock state longer under higher temperature threshold before dropping to a secondary temperature setting base clock. | +| H.264, H.265 and HEVC encode/decode engines | Enables faster than real-time performance for transcoding, video editing, and other encoding applications with two dedicated H.264 and HEVC encode engines and a dedicated decode engine that are independent of 3D/compute pipeline. | +| NVIDIA GPU boost 4.0 | Maximizes application performance automatically without exceeding the power and thermal envelope of the GPU. Allows applications to stay within the boost clock state longer under higher temperature threshold before dropping to a secondary temperature setting base clock. | **Table 2. Quadro RTX tech specs** @@ -67,7 +66,7 @@ Surface Book 3 with Quadro RTX 3000 delivers the best graphics performance of an | NVIDIA RT Cores | 30 | | Tensor Cores | 240 | | GPU memory | 6 GB | -| Memory bandwidth | 288 GBps | +| Memory bandwidth | 288 Gbps | | Memory type | GDDR6 | | Memory interface | 192-bit | | TGP max power consumption | 65W | @@ -87,7 +86,7 @@ Surface Book 3 with Quadro RTX 3000 delivers the best graphics performance of an ## App acceleration -The following table shows how Quadro RTX 3000 provides significantly faster acceleration across leading professional applications. It includes SPECview perf 13 benchmark test results comparing Surface Book 3 15-inch with NVIDIA with Quadro RTX 3000 versus Surface Book 2 15-inch with NVIDIA GeForce GTX 1060 devices in market March 2020. +The following table shows how Quadro RTX 3000 provides significantly faster acceleration across leading professional applications. It includes SPECview perf 13 benchmark test results comparing Surface Book 3 15-inch with NVIDIA Quadro RTX 3000 versus Surface Book 2 15-inch with NVIDIA GeForce GTX 1060 devices in market March 2020. **Table 3. App acceleration on Surface Book 3 with Quadro RTX 3000** @@ -122,8 +121,6 @@ The following table shows how Quadro RTX 3000 provides significantly faster acce | 15-inch | Quad-core 10th Gen Core i7-1065G7 | Intel Iris™ Plus Graphics
NVIDIA Quadro RTX 3000. Max-Q Design with 6GB GDDR6 graphics memory | 32 LPDDR4x | 512 GB | | 15-inch | Quad-core 10th Gen Core i7-1065G7 | Intel Iris™ Plus Graphics
NVIDIA Quadro RTX 3000. Max-Q Design with 6GB GDDR6 graphics memory | 32 LPDDR4x | 1 TB | - - ## Summary Surface Book 3 with Quadro RTX 3000 delivers the best graphics performance on any Surface laptop, providing architects, engineers, developers, and data scientists with the tools they need to work efficiently from anywhere: